© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59627
    Prev
    Next
    INDEX
    Explanations

    Arduino boards and software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    或者
    -2.72
     unſ
    -2.67
    ኧ
    -2.34
    c
    -2.31
    懨
    -2.28
    مشاه
    -2.27
    〮
    -2.19
    Sejarah
    -2.16
    Bagaimana
    -2.16
    或是
    -2.16
    POSITIVE LOGITS
    {
    2.45
    ↵↵
    2.42
    こと
    2.39
     –
    2.17
     と
    2.09
     of
    2.06
     successfully
    2.05
     comprised
    2.03
     outras
    2.00
     utilizing
    1.99
    Activations Density 0.005%

    No Known Activations